weixin_39560002
weixin_39560002
2020-12-08 21:20

yolov3转换 Upsample Layer出错

hi: 感谢开源 我在转成darknet官方的yolov3.cfg yolov3.weights时出错:Check failed: ExactNumBottomBlobs() == bottom.size() (2 vs. 1) Upsample Layer takes 2 bottom blob(s) as input.环境windows10 python3.6

该提问来源于开源项目:ChenYingpeng/darknet2caffe

  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 复制链接分享
  • 邀请回答

4条回答

  • weixin_39581652 weixin_39581652 5月前

    Please check your upsample layer which botton blobs size must be 1. Such as `

    layer { bottom: "layer85-conv" top: "layer86-upsample" name: "layer86-upsample" type: "Upsample" upsample_param { scale: 2 } } `

    点赞 评论 复制链接分享
  • weixin_39835607 weixin_39835607 5月前

    layer { bottom: "layer118-conv" top: "layer119-upsample" name: "layer119-upsample" type: "Upsample" upsample_param { scale: 2 } } 这是我的转换结果,在一些嵌入式AI环境仿真也报同样错误,没看明白为啥。

    点赞 评论 复制链接分享
  • weixin_39835607 weixin_39835607 5月前

    看到网上又用deconv替换upsample的。不知道能否解决

    点赞 评论 复制链接分享
  • weixin_39581652 weixin_39581652 5月前

    Please post more details about your error log.

    点赞 评论 复制链接分享

相关推荐